Agent (KYA)
Is this AI agent who it says it is, and can it be trusted right now? Ward answers with the agent's live KYA Score, trust zone, risk flags and active mandate.
Type: agent · Endpoint: POST /api/v1/kya/verify · Real-time
Request
curl https://api.mandatelabs.ai/api/v1/decide \
-H "X-API-Key: $WARD_API_KEY" -H "Content-Type: application/json" \
-d '{"type": "agent", "input": {"agent_id": "agt_shopper_01"}}'
d = client.decide("agent", {"agent_id": "agt_shopper_01"})
const d = await client.decide("agent", { agent_id: "agt_shopper_01" });
Send agent_id or the agent's W3C agent_did.
Result and decision
| Field | Meaning |
|---|---|
verified |
The agent is registered, active and verified |
kya_score |
0–1; trust zones GREEN ≥ 0.70, AMBER 0.40–0.70, RED 0.20–0.40, CRITICAL < 0.20 |
trust_level, status |
Tier and lifecycle status |
active_mandate |
The mandate in force, if any |
risk_flags |
What lowers trust |
certificate_id |
A signed KYA certificate, verifiable offline with the public keys at /api/v1/kya/jwks.json |
Decision: not verified → DECLINE; verified with risk flags → STEP_UP; verified and clean → APPROVE.